RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks

• URL: http://arxiv.org/abs/2206.06637v2
• Date: Wed, 15 Jun 2022 04:15:28 GMT
• Title: RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks
• Authors: Shanghua Gao, Zhong-Yu Li, Qi Han, Ming-Ming Cheng, Liang Wang
• Abstract summary: We propose to find better receptive field combinations through a global-to-local search scheme. Our search scheme exploits both global search to find the coarse combinations and local search to get the refined receptive field combinations. Our RF-Next models, plugging receptive field search to various models, boost the performance on many tasks.
• Score: 86.6139619721343
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Temporal/spatial receptive fields of models play an important role in sequential/spatial tasks. Large receptive fields facilitate long-term relations, while small receptive fields help to capture the local details. Existing methods construct models with hand-designed receptive fields in layers. Can we effectively search for receptive field combinations to replace hand-designed patterns? To answer this question, we propose to find better receptive field combinations through a global-to-local search scheme. Our search scheme exploits both global search to find the coarse combinations and local search to get the refined receptive field combinations further. The global search finds possible coarse combinations other than human-designed patterns. On top of the global search, we propose an expectation-guided iterative local search scheme to refine combinations effectively. Our RF-Next models, plugging receptive field search to various models, boost the performance on many tasks, e.g., temporal action segmentation, object detection, instance segmentation, and speech synthesis. The source code is publicly available on http://mmcheng.net/rfnext.

Related papers

• Large Search Model: Redefining Search Stack in the Era of LLMs [63.503320030117145]
  We introduce a novel conceptual framework called large search model, which redefines the conventional search stack by unifying search tasks with one large language model (LLM) All tasks are formulated as autoregressive text generation problems, allowing for the customization of tasks through the use of natural language prompts. This proposed framework capitalizes on the strong language understanding and reasoning capabilities of LLMs, offering the potential to enhance search result quality while simultaneously simplifying the existing cumbersome search stack.
  arXiv  Detail & Related papers  (2023-10-23T05:52:09Z)
• OFA$^2$: A Multi-Objective Perspective for the Once-for-All Neural Architecture Search [79.36688444492405]
  Once-for-All (OFA) is a Neural Architecture Search (NAS) framework designed to address the problem of searching efficient architectures for devices with different resources constraints. We aim to give one step further in the search for efficiency by explicitly conceiving the search stage as a multi-objective optimization problem.
  arXiv  Detail & Related papers  (2023-03-23T21:30:29Z)
• CrossBeam: Learning to Search in Bottom-Up Program Synthesis [51.37514793318815]
  We propose training a neural model to learn a hands-on search policy for bottom-up synthesis. Our approach, called CrossBeam, uses the neural model to choose how to combine previously-explored programs into new programs. We observe that CrossBeam learns to search efficiently, exploring much smaller portions of the program space compared to the state-of-the-art.
  arXiv  Detail & Related papers  (2022-03-20T04:41:05Z)
• Exploring Complicated Search Spaces with Interleaving-Free Sampling [127.07551427957362]
  In this paper, we build the search algorithm upon a complicated search space with long-distance connections. We present a simple yet effective algorithm named textbfIF-NAS, where we perform a periodic sampling strategy to construct different sub-networks. In the proposed search space, IF-NAS outperform both random sampling and previous weight-sharing search algorithms by a significant margin.
  arXiv  Detail & Related papers  (2021-12-05T06:42:48Z)
• Global2Local: Efficient Structure Search for Video Action Segmentation [64.99046987598075]
  We propose to find better receptive field combinations through a global-to-local search scheme. Our scheme exploits both global search to find the coarse combinations and local search to get the refined receptive field combination patterns. Our global-to-local search can be plugged into existing action segmentation methods to achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2021-01-04T12:06:03Z)
• DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks [45.075163625895286]
  We search for a meta graph, which can capture more complex semantic relations than a meta path, to determine how graph neural networks propagate messages along different types of edges. We design an expressive search space in the form of a directed acyclic graph (DAG) to represent candidate meta graphs for a HIN. We propose a novel and efficient search algorithm to make the total search cost on a par with training a single GNN once.
  arXiv  Detail & Related papers  (2020-10-07T08:09:29Z)
• NASE: Learning Knowledge Graph Embedding for Link Prediction via Neural Architecture Search [9.634626241415916]
  Link prediction is the task of predicting missing connections between entities in the knowledge graph (KG) Previous work has tried to use Automated Machine Learning (AutoML) to search for the best model for a given dataset. We propose a novel Neural Architecture Search (NAS) framework for the link prediction task.
  arXiv  Detail & Related papers  (2020-08-18T03:34:09Z)
• Deep-n-Cheap: An Automated Search Framework for Low Complexity Deep Learning [3.479254848034425]
  We present Deep-n-Cheap -- an open-source AutoML framework to search for deep learning models. Our framework is targeted for deployment on both benchmark and custom datasets. Deep-n-Cheap includes a user-customizable complexity penalty which trades off performance with training time or number of parameters.
  arXiv  Detail & Related papers  (2020-03-27T13:00:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.